The goal in this work has been to identify the neuronal elements of the cortical column that are most likely to support the learning of nonlinear associative maps. We show that a particular style of network learning algorithm based on locally-tuned receptive fields maps naturally onto cortical hardware, and gives coherence to a variety of features of cortical anatomy, physiology, and biophysics whose relations to learning remain poorly understood.

Data is usually available in the form of a set S consisting of {x,y} pairs, where x is a input vector and y is the corresponding output vector.

We have done an empirical study of the relation of the number of parameters (weights) in a feedforward net to generalization performance.

Eight neural net and conventional pattern classifiers (Bayesianunimodal Gaussian,k-nearest neighbor, standard back-propagation, adaptive-stepsize back-propagation, hypersphere, feature-map, learning vectorquantizer, and binary decision tree) were implemented on a serial computer and compared using two speech recognition and two artificial tasks. Error rates were statistically equivalent on almost all tasks, but classifiers differed by orders of magnitude in memory requirements, training time, classification time, and ease of adaptivity. Nearest-neighbor classifiers trained rapidly but required themost memory. Tree classifiers provided rapid classification but were complex to adapt. Back-propagation classifiers typically requiredlong training times and had intermediate memory requirements. These results suggest that classifier selection should often depend more heavily on practical considerations concerning memory and computation resources, and restrictions on training and classification times than on error rate.

Two approaches were explored which integrate neural net classifiers with Hidden Markov Model (HMM) speech recognizers.

One popular class of unsupervised algorithms are competitive algorithms. Inthe traditional view of competition, only one competitor, the winner, adapts for any given case. I propose to view competitive adaptationas attempting to fit a blend of simple probability generators (such as gaussians) to a set of data-points. The maximum likelihoodfit of a model of this type suggests a "softer" form of competition, in which all competitors adapt in proportion to the relative probability that the input came from each competitor. I investigate one application of the soft competitive model, placement ofradial basis function centers for function interpolation, and show that the soft model can give better performance with little additional computational cost. 1 INTRODUCTION Interest in unsupervised learning has increased recently due to the application of more sophisticated mathematical tools (Linsker, 1988; Plumbley and Fallside, 1988; Sanger, 1989) and the success of several elegant simulations of large scale selforganization (Linsker,1986; Kohonen, 1982). One popular class of unsupervised algorithms are competitive algorithms, which have appeared as components in a variety of systems (Von der Malsburg, 1973; Fukushima, 1975; Grossberg, 1978). Generalizing the definition of Rumelhart and Zipser (1986), a competitive adaptive system consists of a collection of modules which are structurally identical except, possibly, for random initial parameter variation.

The paper suggests a statistical framework for the parameter estimation problemassociated with unsupervised learning in a neural network, leading to an exploratory projection pursuit network that performs feature extraction, or dimensionality reduction.

This paper explores the use of a model neural network for motor learning. Steinbuch and Taylor presented neural network designs to do nearest neighbor lookup in the early 1960s. In this paper their nearest neighbor network is augmented with a local model network, which fits a local model to a set of nearest neighbors. The network design is equivalent to local regression. This network architecture can represent smooth nonlinear functions, yet has simple training rules with a single global optimum.

On 15-16 November 1989, I attended the Massachusetts Institute of Technology (MIT) Industrial Liaison Program entitled "Networks and Learning." The topic was neural networks, their power, potential, and promise. A dozen distinguished professors and researchers presented informative and entertaining talks to an audience of technically minded business executives and industrial researchers who subscribe to MIT's popular series of symposia offered through their Industrial Liaison Program. This informal report encapsulates the two-day event with a brief summary of each talk.

Background The overall aim of our work is to develop fast and flexible systems for image recognition, usually for commercial inspection tasks. There is an urgent need for automatic learning systems in such applications, since at present most systems employ heuristic classification techniques. This approach requires an extensive development effort for each new application, which exaggerates implementation costs; and for many tasks, there are no clearly defined features which can be employed for classification. Enquiring of a human expert will often only produce "good" and "bad" examples of each class and not the underlying strategies which he may employ. Our approach is to model in a quite abstract way the perceptual networks found in the mammalian brain for vision. A back-propagation network could be employed to generalise about the input pattern space, and it would find some useful representations. However, there are many difficulties with this approach, since the network structure assumes nothing about the input space and it can be difficult to bound complicated feature clusters using hyperplanes. The mammalian brain is a layered structure, and so another model may be proposed which involves the application of many two-dimensional feature maps. Each map takes information from the output of the preceding one and performs some type of clustering analysis in order to reduce the dimensionality of the input information.